Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 159 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0599. Min Act: -0.0003

Data Index: 1008612 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0599. Min Act: -0.0003

Data Index: 923438 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0585. Min Act: -0.0003

Data Index: 603056 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0567. Min Act: -0.0003

Data Index: 112281 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0569. Min Act: -0.0004

Data Index: 369736 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0560. Min Act: -0.0003

Data Index: 610226 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0515. Min Act: -0.0003

Data Index: 582717 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0536. Min Act: -0.0003

Data Index: 1066070 (C4 (Web Text))

Max Activating Token Index: 361

Text #8

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0535. Min Act: -0.0004

Data Index: 438743 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0534. Min Act: -0.0003

Data Index: 481842 (C4 (Web Text))

Max Activating Token Index: 968

Text #10

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0532. Min Act: -0.0003

Data Index: 1258974 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0522. Min Act: -0.0003

Data Index: 1343355 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0522. Min Act: -0.0003

Data Index: 931752 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0538. Min Act: -0.0003

Data Index: 1060966 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0531. Min Act: -0.0003

Data Index: 254371 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0529. Min Act: -0.0004

Data Index: 186828 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0527. Min Act: -0.0003

Data Index: 769308 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0526. Min Act: -0.0003

Data Index: 181430 (C4 (Web Text))

Max Activating Token Index: 813

Text #18

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0534. Min Act: -0.0003

Data Index: 1066324 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0521. Min Act: -0.0003

Data Index: 179475 (C4 (Web Text))

Max Activating Token Index: 828